Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron detects formal publication boilerplate and disclaimer language (e.g., journal content notices and “not responsible” style statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     překlad
    -0.07
    <Contact
    -0.06
     vot
    -0.06
     customer
    -0.06
    ело
    -0.06
    asset
    -0.06
     convin
    -0.06
     quartz
    -0.06
     downloads
    -0.05
     Paint
    -0.05
    POSITIVE LOGITS
     za
    0.07
    irteen
    0.06
    раз
    0.06
     Vernon
    0.06
    alla
    0.06
    enticator
    0.06
    langs
    0.06
     dzieci
    0.06
    _pb
    0.06
     Kansas
    0.06
    Act Density 0.002%

    No Known Activations